TECHNOLOGY PROFILE · TECH-0207
promptfoo
Configuration-driven prompt/model testing and red-teaming toolkit.
Core capability checked in primary documentation. This profile preserves the prepared catalog’s original descriptions. Advantages depend on the workload; comparisons are editorial, not benchmark results.
Where it has an edge
Repeatable provider comparisons and regression tests fit CI better than manual chat testing.
Best-fit problems
Testing prompt changes, providers and application-level risks.
Tradeoffs & cautions
Generated tests and model graders need calibration; passing is not a safety certificate.
What to test before choosing
Calibrate scorers on human-labeled cases; fix versions, sampling settings and confidence intervals before comparing.
Runtime & hardware
Local or evaluation workers
Access & licensing
Open-source cores; model/API evaluation costs separate
Execution
Local / self-hosted
Lifecycle
Not independently audited
Comparison basis
Editorial problem-fit judgement; no head-to-head benchmark performed
Connected concepts
Alternatives to investigate
Inspect AI · DeepEval · garak